Bump beautifulsoup4 from 4.10.0 to 4.11.1 (#1717)

* Bump beautifulsoup4 from 4.10.0 to 4.11.1

Bumps [beautifulsoup4](https://www.crummy.com/software/BeautifulSoup/bs4/) from 4.10.0 to 4.11.1.

---
updated-dependencies:
- dependency-name: beautifulsoup4
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

* Update beautifulsoup4==4.11.1

* Update soupsieve==2.3.2.post1

* Update requirements.txt

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: JonnyWong16 <9099342+JonnyWong16@users.noreply.github.com>

[skip ci]
This commit is contained in:
dependabot[bot] 2022-05-16 20:46:21 -07:00 committed by GitHub
parent a1fe0b04d7
commit 467ae352f5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
28 changed files with 4846 additions and 2609 deletions

View file

@ -22,6 +22,7 @@ from bs4.element import (
XMLProcessingInstruction,
)
from bs4.builder import (
DetectsXMLParsedAsHTML,
FAST,
HTML,
HTMLTreeBuilder,
@ -79,15 +80,24 @@ class LXMLTreeBuilderForXML(TreeBuilder):
This might be useful later on when creating CSS selectors.
This will track (almost) all namespaces, even ones that were
only in scope for part of the document. If two namespaces have
the same prefix, only the first one encountered will be
tracked. Un-prefixed namespaces are not tracked.
:param mapping: A dictionary mapping namespace prefixes to URIs.
"""
for key, value in list(mapping.items()):
# This is 'if key' and not 'if key is not None' because we
# don't track un-prefixed namespaces. Soupselect will
# treat an un-prefixed namespace as the default, which
# causes confusion in some cases.
if key and key not in self.soup._namespaces:
# Let the BeautifulSoup object know about a new namespace.
# If there are multiple namespaces defined with the same
# prefix, the first one in the document takes precedence.
self.soup._namespaces[key] = value
def default_parser(self, encoding):
"""Find the default parser for the given encoding.
@ -125,6 +135,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
self.empty_element_tags = set(empty_element_tags)
self.soup = None
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
self.active_namespace_prefixes = [dict(self.DEFAULT_NSMAPS)]
super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
def _getNsTag(self, tag):
@ -166,12 +177,21 @@ class LXMLTreeBuilderForXML(TreeBuilder):
is_html = not self.is_xml
if is_html:
self.processing_instruction_class = ProcessingInstruction
# We're in HTML mode, so if we're given XML, that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
else:
self.processing_instruction_class = XMLProcessingInstruction
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
# TODO: This is a workaround for
# https://bugs.launchpad.net/lxml/+bug/1948551.
# We can remove it once the upstream issue is fixed.
if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}':
markup = markup[1:]
yield markup, None, document_declared_encoding, False
if isinstance(markup, str):
@ -240,6 +260,20 @@ class LXMLTreeBuilderForXML(TreeBuilder):
# mappings.
self.nsmaps.append(_invert(nsmap))
# The currently active namespace prefixes have
# changed. Calculate the new mapping so it can be stored
# with all Tag objects created while these prefixes are in
# scope.
current_mapping = dict(self.active_namespace_prefixes[-1])
current_mapping.update(nsmap)
# We should not track un-prefixed namespaces as we can only hold one
# and it will be recognized as the default namespace by soupsieve,
# which may be confusing in some situations.
if '' in current_mapping:
del current_mapping['']
self.active_namespace_prefixes.append(current_mapping)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
@ -264,8 +298,11 @@ class LXMLTreeBuilderForXML(TreeBuilder):
namespace, name = self._getNsTag(name)
nsprefix = self._prefix_for_namespace(namespace)
self.soup.handle_starttag(name, namespace, nsprefix, attrs)
self.soup.handle_starttag(
name, namespace, nsprefix, attrs,
namespaces=self.active_namespace_prefixes[-1]
)
def _prefix_for_namespace(self, namespace):
"""Find the currently active prefix for the given namespace."""
if namespace is None:
@ -289,13 +326,20 @@ class LXMLTreeBuilderForXML(TreeBuilder):
if len(self.nsmaps) > 1:
# This tag, or one of its parents, introduced a namespace
# mapping, so pop it off the stack.
self.nsmaps.pop()
out_of_scope_nsmap = self.nsmaps.pop()
if out_of_scope_nsmap is not None:
# This tag introduced a namespace mapping which is no
# longer in scope. Recalculate the currently active
# namespace prefixes.
self.active_namespace_prefixes.pop()
def pi(self, target, data):
self.soup.endData()
self.soup.handle_data(target + ' ' + data)
data = target + ' ' + data
self.soup.handle_data(data)
self.soup.endData(self.processing_instruction_class)
def data(self, content):
self.soup.handle_data(content)